Data preprocessing for Occipital Lobe

---

Raw data

Dataset downloaded from mgandal’s github repository.

Load and annotate data

# Load csvs
datExpr = read.csv('./../Data/RNAseq_ASD_datExpr.csv', row.names=1)
datMeta = read.csv('./../Data/RNAseq_ASD_datMeta.csv')

# 1. Group brain regions by lobes
# 2. Remove '/' from Batch variable: (It is recommended (but not required) to use only letters, numbers, 
#    and delimiters '_' or '.', in levels of factors as these are safe characters for column names in R
# 3. Transform Diagnosis into a factor variable
datMeta = datMeta %>% mutate(Brain_Region = as.factor(Region)) %>% 
                      mutate(Brain_lobe = ifelse(Brain_Region %in% c('BA4_6', 'BA9', 'BA24', 'BA44_45'), 'Frontal',
                                          ifelse(Brain_Region %in% c('BA3_1_2_5', 'BA7'), 'Parietal',
                                          ifelse(Brain_Region %in% c('BA38', 'BA39_40', 'BA20_37', 'BA41_42_22'), 'Temporal',
                                          'Occipital')))) %>%
                      mutate(Batch = as.factor(gsub('/', '.', RNAExtractionBatch)), 
                             Diagnosis = factor(Diagnosis_, levels=c('CTL','ASD'))) %>% 
                      dplyr::select(-Diagnosis_)

# Filter to only keep Frontal Lobe samples
datMeta = datMeta %>% filter(Brain_lobe=='Occipital')
datExpr = datExpr %>% dplyr::select(which(colnames(datExpr) %in% paste0('X',gsub('-','_',datMeta$X))))


# GO Neuronal annotations: regex 'neuron' in GO functional annotations and label the genes that make a match as neuronal
GO_annotations = read.csv('./../Data/genes_GO_annotations.csv')
GO_neuronal = GO_annotations %>% filter(grepl('neuron', go_term)) %>% 
              mutate('ID'=as.character(ensembl_gene_id)) %>% 
              dplyr::select(-ensembl_gene_id) %>% distinct(ID) %>%
              mutate('Neuronal'=1)


# SFARI Genes
SFARI_genes = read_csv('./../../../SFARI/Data/SFARI_genes_08-29-2019_w_ensembl_IDs.csv')
SFARI_genes = SFARI_genes[!duplicated(SFARI_genes$ID) & !is.na(SFARI_genes$ID),]

# NCBI biotype annotation
NCBI_biotype = read.csv('./../../../NCBI/Data/gene_biotype_info.csv') %>% 
               rename(Ensembl_gene_identifier='ensembl_gene_id', type_of_gene='gene_biotype', Symbol='hgnc_symbol') %>% 
               mutate(gene_biotype = ifelse(gene_biotype=='protein-coding','protein_coding',gene_biotype))

rm(GO_annotations)

Check sample composition

Data description taken from the dataset’s synapse entry: RNAseq data was generated from 88 postmortem cortex brain samples from subjects with ASD (53 samples from 24 subjects) and non-psychiatric controls (35 samples from 17 subjects), across four cortical regions encompassing all major cortical lobes – frontal, temporal, parietal, and occipital. Brain samples were obtained from the Harvard Brain Bank as part of the Autism Tissue Project (ATP).

cat(paste0('Dataset includes ', nrow(datExpr), ' genes from ', ncol(datExpr), ' samples belonging to ', 
             length(unique(datMeta$Subject_ID)), ' different subjects.'))

## Dataset includes 63682 genes from 23 samples belonging to 23 different subjects.

Counts distribution: More than half of the counts are zero and most of the counts are relatively low, but there are some very high outliers

count_distr = summary(melt(datExpr))[,2]
for(i in 1:6){
  print(count_distr[i])
}

##                      
## "Min.   :       0  " 
##                      
## "1st Qu.:       0  " 
##                      
## "Median :       0  " 
##                      
## "Mean   :     565  " 
##                      
## "3rd Qu.:      26  " 
##                      
## "Max.   :25859990  "

rm(count_distr, i)

Diagnosis distribution by Sample: There are more ASD samples than controls

table_info = datMeta %>% apply_labels(Diagnosis = 'Diagnosis', Brain_lobe = 'Brain Lobe', Batch = 'Batch', Sex = 'Gender')
cro(table_info$Diagnosis)

	#Total
Diagnosis
CTL	8
ASD	15
#Total cases	23

Sex distribution: There are many more Male samples than Female ones

cro(table_info$Sex)

	#Total
Gender
F	5
M	18
#Total cases	23

Diagnosis and Gender seem to be relatively balanced

cro(table_info$Diagnosis, list(table_info$Sex, total()))

	Gender			#Total
	F	M
Diagnosis
CTL	1	7		8
ASD	4	11		15
#Total cases	5	18		23

Age distribution: Subjects between 2 and 56 years old with a mean of 27

summary(datMeta$Age)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    5.00   16.50   24.00   26.61   35.00   54.00

Annotate genes with BioMart information

I was originally running this with the feb2014 version of BioMart because that’s the one that Gandal used (and it finds all of the Ensembl IDs, which other versions don’t), but it has some outdated biotype annotations, to fix this I’ll obtain all the information except the biotype label from BioMart in the same way as it had been done before, and then I’ll add the most current biotype label using information from NCBI’s website and then from BioMart in the following way:

1.Use BioMart to run a query with the original feb2014 version using the Ensembl IDs as keys to obtain all the information except the biotype labels

2. Annotate genes with Biotype labels:

2.1 Use the NCBI annotations downloaded from NCBI’s website and processed in NCBI/RMarkdowns/20_02_07_clean_data.html (there is information for only 26K genes, so some genes will remain unlabelled)

2.2 Use the current version (jan2020) to obtain the biotype annotations using the Ensembl ID as keys (some genes don’t return a match)

2.3 For the genes that didn’t return a match, use the current version (jan2020) to obtain the biotype annotations using the gene name as keys (17 genes return multiple labels)

2.4 For the genes that returned multiple labels, use the feb2014 version with the Ensembl IDs as keys

labels_source = data.frame(data.frame('source' = c('NCBI', 'BioMart2020_byID', 'BioMart2020_byGene', 'BioMart2014'),
                                      'n_matches' = rep(0,4)))

########################################################################################
# 1. Query archive version

getinfo = c('ensembl_gene_id','external_gene_id','chromosome_name','start_position',
            'end_position','strand')
mart = useMart(biomart='ENSEMBL_MART_ENSEMBL', dataset='hsapiens_gene_ensembl', host='feb2014.archive.ensembl.org')
datGenes = getBM(attributes=getinfo, filters=c('ensembl_gene_id'), values=rownames(datExpr), mart=mart) %>% 
           rename(external_gene_id = 'hgnc_symbol')

## Cache found

datGenes$length = datGenes$end_position-datGenes$start_position

cat(paste0('1. ', sum(is.na(datGenes$start_position)), '/', nrow(datGenes),
             ' Ensembl IDs weren\'t found in the feb2014 version of BioMart'))

## 1. 0/63677 Ensembl IDs weren't found in the feb2014 version of BioMart

########################################################################################
########################################################################################
# 2. Get Biotype Labels

cat('2. Add biotype information')

## 2. Add biotype information

########################################################################################
# 2.1 Add NCBI annotations
datGenes = datGenes %>% left_join(NCBI_biotype, by=c('ensembl_gene_id','hgnc_symbol'))

cat(paste0('2.1 ' , sum(is.na(datGenes$gene_biotype)), '/', nrow(datGenes),
             ' Ensembl IDs weren\'t found in the NCBI database'))

## 2.1 42904/63677 Ensembl IDs weren't found in the NCBI database

labels_source$n_matches[1] = sum(!is.na(datGenes$gene_biotype))

########################################################################################
# 2.2 Query current BioMart version for gene_biotype using Ensembl ID as key

getinfo = c('ensembl_gene_id','gene_biotype')
mart = useMart(biomart='ENSEMBL_MART_ENSEMBL', dataset='hsapiens_gene_ensembl', host='jan2020.archive.ensembl.org')
datGenes_biotype = getBM(attributes=getinfo, filters=c('ensembl_gene_id'), mart=mart, 
                         values=datGenes$ensembl_gene_id[is.na(datGenes$gene_biotype)])

## Cache found

cat(paste0('2.2 ' , sum(is.na(datGenes$gene_biotype))-nrow(datGenes_biotype), '/', sum(is.na(datGenes$gene_biotype)),
             ' Ensembl IDs weren\'t found in the jan2020 version of BioMart when querying by Ensembl ID'))

## 2.2 9099/42904 Ensembl IDs weren't found in the jan2020 version of BioMart when querying by Ensembl ID

# Add new gene_biotype info to datGenes
datGenes = datGenes %>% left_join(datGenes_biotype, by='ensembl_gene_id') %>%
           mutate(gene_biotype = coalesce(as.character(gene_biotype.x), gene_biotype.y)) %>%
           dplyr::select(-gene_biotype.x, -gene_biotype.y)

labels_source$n_matches[2] = sum(!is.na(datGenes$gene_biotype)) - labels_source$n_matches[1]

########################################################################################
# 3. Query current BioMart version for gene_biotype using gene symbol as key

missing_genes = unique(datGenes$hgnc_symbol[is.na(datGenes$gene_biotype)])
getinfo = c('hgnc_symbol','gene_biotype')
datGenes_biotype_by_gene = getBM(attributes=getinfo, filters=c('hgnc_symbol'), mart=mart,
                                 values=missing_genes)

## Cache found

cat(paste0('2.3 ', length(missing_genes)-length(unique(datGenes_biotype_by_gene$hgnc_symbol)),'/',length(missing_genes),
             ' genes weren\'t found in the current BioMart version when querying by gene name'))

## 2.3 5712/7866 genes weren't found in the current BioMart version when querying by gene name

dups = unique(datGenes_biotype_by_gene$hgnc_symbol[duplicated(datGenes_biotype_by_gene$hgnc_symbol)])
cat(paste0('    ', length(dups), ' genes returned multiple labels (these won\'t be added)'))

##     17 genes returned multiple labels (these won't be added)

# Update information
datGenes_biotype_by_gene = datGenes_biotype_by_gene %>% filter(!hgnc_symbol %in% dups)
datGenes = datGenes %>% left_join(datGenes_biotype_by_gene, by='hgnc_symbol') %>% 
            mutate(gene_biotype = coalesce(gene_biotype.x, gene_biotype.y)) %>%
            dplyr::select(-gene_biotype.x, -gene_biotype.y)

labels_source$n_matches[3] = sum(!is.na(datGenes$gene_biotype)) - sum(labels_source$n_matches)

########################################################################################
# 4. Query feb2014 BioMart version for the missing biotypes

missing_ensembl_ids = unique(datGenes$ensembl_gene_id[is.na(datGenes$gene_biotype)])

getinfo = c('ensembl_gene_id','gene_biotype')
mart = useMart(biomart='ENSEMBL_MART_ENSEMBL', dataset='hsapiens_gene_ensembl', host='feb2014.archive.ensembl.org')
datGenes_biotype_archive = getBM(attributes=getinfo, filters=c('ensembl_gene_id'), values=missing_ensembl_ids, mart=mart)

## Cache found

cat(paste0('2.4 ', length(missing_ensembl_ids)-nrow(datGenes_biotype_archive),'/',length(missing_ensembl_ids),
             ' genes weren\'t found in the feb2014 BioMart version when querying by Ensembl ID'))

## 2.4 0/6648 genes weren't found in the feb2014 BioMart version when querying by Ensembl ID

# Update information
datGenes = datGenes %>% left_join(datGenes_biotype_archive, by='ensembl_gene_id') %>% 
            mutate(gene_biotype = coalesce(gene_biotype.x, gene_biotype.y)) %>%
            dplyr::select(-gene_biotype.x, -gene_biotype.y)

labels_source$n_matches[4] = sum(!is.na(datGenes$gene_biotype)) - sum(labels_source$n_matches)

########################################################################################
# Plot results

labels_source = labels_source %>% mutate(x = 1, percentage = round(100*n_matches/sum(n_matches),1))

p = labels_source %>% ggplot(aes(x, percentage, fill=source)) + geom_bar(position = 'stack', stat = 'identity') +
    theme_minimal() + coord_flip() + theme(legend.position='bottom', axis.title.y=element_blank(),
    axis.text.y=element_blank(), axis.ticks.y=element_blank())

ggplotly(p + theme(legend.position='none'))

as_ggplot(get_legend(p))

########################################################################################
# Reorder rows to match datExpr
datGenes = datGenes[match(rownames(datExpr), datGenes$ensembl_gene_id),]


rm(getinfo, mart, datGenes_biotype, datGenes_biotype_by_gene, datGenes_biotype_archive,
   dups, missing_ensembl_ids, missing_genes, labels_source, p)

---

Filtering

Checking how many SFARI genes are in the dataset

df = SFARI_genes %>% dplyr::select(-gene_biotype) %>% inner_join(datGenes, by=c('ID'='ensembl_gene_id'))

cat(paste0('Considering all genes, this dataset contains ', length(unique(df$`gene-symbol`)),
             ' of the ', length(unique(SFARI_genes$`gene-symbol`)), ' SFARI genes\n\n'))

## Considering all genes, this dataset contains 979 of the 980 SFARI genes

cat(paste0('The missing gene is ',
           SFARI_genes$`gene-symbol`[! SFARI_genes$`gene-symbol` %in% df$`gene-symbol`],
           ' with a SFARI score of ',
           SFARI_genes$`gene-score`[! SFARI_genes$`gene-symbol` %in% df$`gene-symbol`]))

## The missing gene is MIR137 with a SFARI score of 3

rm(df)

1. Filter entries that don’t correspond to genes

to_keep = !is.na(datGenes$length)
cat(paste0('Names of the rows removed: ', paste(rownames(datExpr)[!to_keep], collapse=', ')))

## Names of the rows removed: __no_feature, __ambiguous, __too_low_aQual, __not_aligned, __alignment_not_unique

datGenes = datGenes[to_keep,]
datExpr = datExpr[to_keep,]
rownames(datGenes) = datGenes$ensembl_gene_id

cat(paste0('Removed ', sum(!to_keep), ' \'genes\', ', sum(to_keep), ' remaining'))

## Removed 5 'genes', 63677 remaining

2. Filter genes that do not encode any protein

cat(paste0(sum(datGenes$gene_biotype=='protein_coding'), '/', nrow(datGenes), ' are protein coding genes' ))

## 22543/63677 are protein coding genes

sort(table(datGenes$gene_biotype), decreasing=TRUE)

## 
##                     protein_coding                             lncRNA 
##                              22543                              12167 
##               processed_pseudogene             unprocessed_pseudogene 
##                              10117                               2547 
##                                  1                              miRNA 
##                               2314                               2276 
##                           misc_RNA                              snRNA 
##                               2178                               2043 
##                         pseudogene                             snoRNA 
##                               1410                               1202 
##                            lincRNA transcribed_unprocessed_pseudogene 
##                                840                                682 
##                    rRNA_pseudogene   transcribed_processed_pseudogene 
##                                500                                441 
##                          antisense                                  3 
##                                380                                331 
##                                  6                    IG_V_pseudogene 
##                                314                                254 
##                          IG_V_gene                          TR_V_gene 
##                                179                                146 
##     transcribed_unitary_pseudogene                          TR_J_gene 
##                                 86                                 81 
##                 unitary_pseudogene               processed_transcript 
##                                 74                                 72 
##                     sense_intronic                          IG_D_gene 
##                                 72                                 64 
##                               rRNA                    TR_V_pseudogene 
##                                 49                                 46 
##                  sense_overlapping                             scaRNA 
##                                 38                                 31 
##             polymorphic_pseudogene                                  7 
##                                 28                                 25 
##                          IG_J_gene                          IG_C_gene 
##                                 24                                 23 
##                            Mt_tRNA                                  4 
##                                 22                                 17 
##                    IG_C_pseudogene                                TEC 
##                                 11                                 11 
##                          TR_C_gene           3prime_overlapping_ncrna 
##                                  8                                  6 
##                    IG_J_pseudogene                           ribozyme 
##                                  6                                  5 
##                    TR_J_pseudogene                          TR_D_gene 
##                                  5                                  3 
##                            Mt_rRNA                                  8 
##                                  2                                  1 
##    translated_processed_pseudogene  translated_unprocessed_pseudogene 
##                                  1                                  1 
##                           vaultRNA 
##                                  1

Most of the genes with low expression levels are not protein-coding

plot_data = data.frame('ID' = rownames(datExpr), 'MeanExpr' = apply(datExpr, 1, mean),
                       'ProteinCoding' = datGenes$gene_biotype=='protein_coding')

ggplotly(plot_data %>% ggplot(aes(log2(MeanExpr+1), fill=ProteinCoding, color=ProteinCoding)) + geom_density(alpha=0.5) + 
         theme_minimal())

rm(plot_data)

We lose 3 genes with a SFARI score

Note: The gene name for Ensembl ID ENSG00000187951 is wrong, it should be AC091057.1 instead of ARHGAP11B, but the biotype is right, so it would still be filtered out

df = SFARI_genes %>% dplyr::select(-gene_biotype) %>% inner_join(datGenes, by=c('ID'='ensembl_gene_id'))

cat(paste0('Filtering protein coding genes, we are left with ', length(unique(df$`gene-symbol`[df$gene_biotype=='protein_coding'])),
             ' SFARI genes'))

## Filtering protein coding genes, we are left with 976 SFARI genes

kable(df %>% filter(! `gene-symbol` %in% df$`gene-symbol`[df$gene_biotype=='protein_coding']) %>% 
      dplyr::select(ID, `gene-symbol`, `gene-score`, gene_biotype, syndromic, `number-of-reports`), caption='Lost Genes')

Lost Genes

ID	gene-symbol	gene-score	gene_biotype	syndromic	number-of-reports
ENSG00000187951	ARHGAP11B	4	lncRNA	0	2
ENSG00000251593	MSNP1AS	2	processed_pseudogene	0	12
ENSG00000197558	SSPO	4	transcribed_unitary_pseudogene	0	3

rm(df)

if(!all(rownames(datExpr)==rownames(datGenes))) cat('!!! gene rownames do not match!!!')

to_keep = datGenes$gene_biotype=='protein_coding'
datExpr = datExpr %>% filter(to_keep)
datGenes = datGenes %>% filter(to_keep)
rownames(datExpr) = datGenes$ensembl_gene_id
rownames(datGenes) = datGenes$ensembl_gene_id

cat(paste0(length(unique(SFARI_genes$`gene-symbol`[SFARI_genes$ID %in% rownames(datExpr)])), ' SFARI genes remaining'))

## 976 SFARI genes remaining

cat(paste0('Removed ', sum(!to_keep), ' genes, ', sum(to_keep), ' remaining'))

## Removed 41134 genes, 22543 remaining

3. Filter genes with low expression levels

\(\qquad\) 3.1 Remove genes with zero expression in all of the samples

to_keep = rowSums(datExpr)>0

cat(paste0('Removed ', sum(!to_keep), ' genes, ', sum(to_keep), ' remaining'))

## Removed 3830 genes, 18713 remaining

df = data.frame('rowSums' = rowSums(datExpr), 'ensembl_gene_id' = rownames(datExpr)) %>%
     right_join(SFARI_genes, by='ensembl_gene_id') %>% filter(rowSums==0 & `gene-score` %in% c(1,2,3)) %>%
     arrange(`gene-score`) %>% dplyr::select(-ensembl_gene_id) %>% filter(!duplicated(`gene-symbol`))

kable(df %>% dplyr::select(ID, `gene-symbol`, `gene-score`, gene_biotype, syndromic, `number-of-reports`), 
      caption='Lost Genes with Top Scores')

Lost Genes with Top Scores

ID	gene-symbol	gene-score	gene_biotype	syndromic	number-of-reports
ENSG00000267910	KMT2A	1	protein_coding	1	20
ENSG00000227460	SYNGAP1	1	protein_coding	1	50
ENSG00000265594	CEP41	2	protein_coding	0	5
ENSG00000272883	CNOT3	2	protein_coding	1	5
ENSG00000259938	CUX1	2	protein_coding	0	6
ENSG00000271019	MBOAT7	2	protein_coding	1	3
ENSG00000268563	MECP2	2	protein_coding	1	75
ENSG00000262024	TCF20	2	protein_coding	1	10
ENSG00000266334	APH1A	3	protein_coding	0	2
ENSG00000260508	GGNBP2	3	protein_coding	0	2
ENSG00000272706	GRIK5	3	protein_coding	0	8
ENSG00000269816	KDM5C	3	protein_coding	0	22
ENSG00000235718	MFRP	3	protein_coding	0	6
ENSG00000267946	TMLHE	3	protein_coding	0	5
ENSG00000260150	ZMYND11	3	protein_coding	0	10

datGenes = datGenes[to_keep,]
datExpr = datExpr[to_keep,]

cat(paste0(length(unique(SFARI_genes$`gene-symbol`[SFARI_genes$ID %in% rownames(datExpr)])), ' SFARI genes remaining'))

## 964 SFARI genes remaining

rm(df)

\(\qquad\) 2.2 Removing genes with a high percentage of zeros

Choosing the threshold:

Criteria for selecting the percentage of zeros threshold: The minimum value in which the preprocessed data is relatively homoscedastic (we’re trying to get rid of the group of genes with very low mean and SD that make the cloud of points look like a comic book speech bubble)

• On the plot I’m using the “dual” of the maximum percentage of zeros, the minimum percentage of non zeros so the visualisation is more intuitive

• 57% seems to be a good threshold for the minimum percentage of non zeros, so 43% will be the maximum percentage of zeros allowed in a row

• The Mean vs SD plot doesn’t show all of the genes, a random sample was selected for the genes with higher level of expression so the visualisation wouldn’t be as heavy (and since we care about the genes with the lowest levels of expression, we aren’t losing important information)

datMeta_original = datMeta
datExpr_original = datExpr
datGenes_original = datGenes

# Return to original variables
datExpr = datExpr_original
datGenes = datGenes_original
datMeta = datMeta_original

rm(datExpr_original, datGenes_original, datMeta_original, datExpr_vst, datGenes_vst, datMeta_vst)

Filtering

# Minimum percentage of non-zero entries allowed per gene
threshold = 57

plot_data = data.frame('id'=rownames(datExpr), 'non_zero_percentage' = apply(datExpr, 1, function(x) 100*mean(x>0)))

ggplotly(plot_data %>% ggplot(aes(x=non_zero_percentage)) + geom_density(color='#0099cc', fill='#0099cc', alpha=0.3) + 
         geom_vline(xintercept=threshold, color='gray') + #scale_x_log10() + 
         ggtitle('Percentage of non-zero entries distribution') + theme_minimal())

to_keep = apply(datExpr, 1, function(x) 100*mean(x>0)) >= threshold
datGenes = datGenes[to_keep,]
datExpr = datExpr[to_keep,]

cat(paste0(length(unique(SFARI_genes$`gene-symbol`[SFARI_genes$ID %in% rownames(datExpr)])), ' SFARI genes remaining'))

## 931 SFARI genes remaining

cat(paste0('Removed ', sum(!to_keep), ' genes, ', sum(to_keep), ' remaining'))

## Removed 2223 genes, 16490 remaining

rm(threshold, plot_data, to_keep)

3. Filter outlier samples

\(\qquad\) 3.1 Gandal filters samples belonging to subject AN03345 without giving an explanation. Since it could have some technical problems, I remove them as well

to_keep = (datMeta$Subject_ID != 'AN03345')
datMeta = datMeta[to_keep,]
datExpr = datExpr[,to_keep]

cat(paste0('Removed ', sum(!to_keep), ' samples, ', sum(to_keep), ' remaining'))

## Removed 0 samples, 23 remaining

\(\qquad\) 3.2 Filter out outliers: Using node connectivity as a distance measure, normalising it and filtering out genes farther away than 2 standard deviations from the left (lower connectivity than average, not higher)

• Gandal uses the formula \(s_{ij}=\frac{1+bw(i,j)}{2}\) to convert all the weights to positive values, but I used \(s_{ij}=|bw(i,j)|\) instead because I think it makes more sense. In the end it doesn’t matter because they select as outliers the same six samples

• Two outlier samples were found, both from the ASD group

absadj = datExpr %>% bicor %>% abs

## alpha: 1.000000

netsummary = fundamentalNetworkConcepts(absadj)
ku = netsummary$Connectivity
z.ku = (ku-mean(ku))/sqrt(var(ku))

plot_data = data.frame('sample'=1:length(z.ku), 'distance'=z.ku, 'Sample_ID'=datMeta$Sample_ID, 
                       'Subject_ID'=datMeta$Subject_ID, 'Extraction_Batch'=datMeta$RNAExtractionBatch,
                       'Brain_Lobe'=datMeta$Brain_lobe, 'Sex'=datMeta$Sex, 'Age'=datMeta$Age,
                       'Diagnosis'=datMeta$Diagnosis, 'PMI'=datMeta$PMI)
selectable_scatter_plot(plot_data, plot_data[,-c(1,2)])

cat(paste0('Outlier sample(s): ', paste(as.character(plot_data$Sample_ID[plot_data$distance< -2]), collapse=', ')))

## Outlier sample(s): AN17254_BA17, AN02987_BA17

to_keep = z.ku > -2
datMeta = datMeta[to_keep,]
datExpr = datExpr[,to_keep]

cat(paste0('Removed ', sum(!to_keep), ' samples, ', sum(to_keep), ' remaining'))

## Removed 2 samples, 21 remaining

rm(absadj, netsummary, ku, z.ku, plot_data, to_keep)

cat(paste0('After filtering, the dataset consists of ', nrow(datExpr), ' genes and ', ncol(datExpr), ' samples'))

## After filtering, the dataset consists of 16490 genes and 21 samples

---

Batch Effects

According to Tackling the widespread and critical impact of batch effects in high-throughput data, technical artifacts can be an important source of variability in the data, so batch correction should be part of the standard preprocessing pipeline of gene expression data.

They say Processing group and Date of the experiment are good batch surrogates, so I’m going to see if they affect the data in any clear way to use them as surrogates.

Processing group

All the information we have is the Brain Bank, and although all the samples were obtained from the Autism Tissue Project, we don’t have any more specific information about who preprocessed each sample

table(datMeta$Brain_Bank)

## 
## ATP 
##  21

Date of processing

There are two different dates when the data was procesed

table(datMeta$RNAExtractionBatch)

## 
## 10/10/2014  6/20/2014 
##         14          7

On the whole dataset there wasn’t a correlation betwen batch surrogante and diagnosis, but now that we are filtering for Occipital Lobe samples, all but one of the control samples were processed on the first batch

table(datMeta$RNAExtractionBatch, datMeta$Diagnosis)

##             
##              CTL ASD
##   10/10/2014   7   7
##   6/20/2014    1   6

Samples don’t seem to cluster together that strongly for each batch and I can’t see a confounding effect between batch and diagnosis, but perhaps it’s because there aren’t enough observations

h_clusts = datExpr %>% t %>% dist %>% hclust %>% as.dendrogram

create_viridis_dict = function(){
  min_age = datMeta$Age %>% min
  max_age = datMeta$Age %>% max
  viridis_age_cols = viridis(max_age - min_age + 1)
  names(viridis_age_cols) = seq(min_age, max_age)
  
  return(viridis_age_cols)
}
viridis_age_cols = create_viridis_dict()

dend_meta = datMeta[match(substring(labels(h_clusts),2), datMeta$Dissected_Sample_ID),] %>% 
            mutate('Batch' = ifelse(RNAExtractionBatch=='10/10/2014', '#F8766D', '#00BFC4'),
                   'Diagnosis' = ifelse(Diagnosis=='CTL','#008080','#86b300'), # Blue control, Green ASD
                   'Sex' = ifelse(Sex=='F','#ff6666','#008ae6'),                # Pink Female, Blue Male
                   'Age' = viridis_age_cols[as.character(Age)]) %>%             # Purple: young, Yellow: old
            dplyr::select(Age, Sex, Diagnosis, Batch)
h_clusts %>% as.dendrogram %>% dendextend::set('labels', rep('', nrow(datMeta))) %>% 
             dendextend::set('branches_k_color', k=5) %>% plot
colored_bars(colors=dend_meta)

rm(h_clusts, dend_meta, create_viridis_dict, viridis_age_cols)

Comparing the mean expression of each sample by batch, this time, the difference between batches doesn’t seem that big

plot_data_b1 = data.frame('Mean'=colMeans(datExpr[,datMeta$RNAExtractionBatch=='10/10/2014']), 'Batch'='10/10/2014')
plot_data_b2 = data.frame('Mean'=colMeans(datExpr[,datMeta$RNAExtractionBatch=='6/20/2014']), 'Batch'='6/20/2014')

plot_data = rbind(plot_data_b1, plot_data_b2)
mu = plot_data %>% group_by(Batch) %>% dplyr::summarise(BatchMean=mean(Mean))

ggplotly(plot_data %>% ggplot(aes(x=Mean, color=Batch, fill=Batch)) + geom_density(alpha=0.3) + 
         geom_vline(data=mu, aes(xintercept=BatchMean, color=Batch), linetype='dashed') +
         ggtitle('Mean expression by sample grouped by Batch') + scale_x_log10() + theme_minimal())

rm(plot_data_b1, plot_data_b2, plot_data, mu)

Looking for unknown sources of batch effects

Following the pipeline from Surrogate variable analysis: hidden batch effects where sva is used with DESeq2.

Create a DeseqDataSet object, estimate the library size correction and save the normalized counts matrix

counts = datExpr %>% as.matrix
rowRanges = GRanges(datGenes$chromosome_name,
                  IRanges(datGenes$start_position, width=datGenes$length),
                  strand=datGenes$strand,
                  feature_id=datGenes$ensembl_gene_id)
se = SummarizedExperiment(assays=SimpleList(counts=counts), rowRanges=rowRanges, colData=datMeta)
dds = DESeqDataSet(se, design = ~ Diagnosis)

dds = estimateSizeFactors(dds)
norm.cts = counts(dds, normalized=TRUE)

Provide the normalized counts and two model matrices to SVA. The first matrix uses the biological condition, and the second model matrix is the null model.

mod = model.matrix(~ Diagnosis, colData(dds))
mod0 = model.matrix(~ 1, colData(dds))
sva_fit = svaseq(norm.cts, mod=mod, mod0=mod0)

## Number of significant surrogate variables is:  4 
## Iteration (out of 5 ):1  2  3  4  5

rm(mod, mod0, norm.cts)

Found 4 surrogate variables, since there is no direct way to select which ones to pick Bioconductor answer, kept all of them.

Include SV estimations to datMeta information

sv_data = sva_fit$sv %>% data.frame
colnames(sv_data) = paste0('SV',1:ncol(sv_data))

datMeta_sva = cbind(datMeta, sv_data)

rm(sv_data, sva_fit)

In conclusion: Date of extraction works as a surrogate for batch effect and the sva package found other 5 variables that could work as surrogates which are now included in datMeta and should be included in the DEA.

---

Normalisation and Differential Expression Analysis

Using DESeq2 package to perform normalisation. I chose this package over limma because limma uses the log transformed data as input instead of the raw counts and I have discovered that in this dataset, this transformation affects genes differently depending on their mean expression level, and genes with a high SFARI score are specially affected by this.

plot_data = data.frame('ID'=rownames(datExpr), 'Mean'=rowMeans(datExpr), 'SD'=apply(datExpr,1,sd))

plot_data %>% ggplot(aes(Mean, SD)) + geom_point(color='#0099cc', alpha=0.1) + geom_abline(color='gray') +
              scale_x_log10() + scale_y_log10() + theme_minimal()

rm(plot_data)

• Using vst instead of rlog to perform normalisation. Bioconductor question explaining differences between methods. Chose vst because a) it is much faster than rlog (it is recommended to use vst for samples larger than 50), and b) Michael Love (author of DESEq2) recommends using it over rlog

• Including a log fold change threshold of 0 in the results formula \(H_0:lfc=0\) because setting any other log fold change seems arbitrary and we risk losing genes with a significant differential expression for genes with a higher fold change, but not necessarily as significant.

counts = datExpr %>% as.matrix
rowRanges = GRanges(datGenes$chromosome_name,
                  IRanges(datGenes$start_position, width=datGenes$length),
                  strand=datGenes$strand,
                  feature_id=datGenes$ensembl_gene_id)
se = SummarizedExperiment(assays=SimpleList(counts=counts), rowRanges=rowRanges, colData=datMeta_sva)
dds = DESeqDataSet(se, design = ~ Batch + SV1 + SV2 + SV3 + SV4 + Diagnosis)

# Perform DEA
dds = DESeq(dds)

## estimating size factors

## estimating dispersions

## gene-wise dispersion estimates

## mean-dispersion relationship

## final dispersion estimates

## fitting model and testing

DE_info = results(dds, lfcThreshold=0, altHypothesis='greaterAbs')

# Perform vst
vsd = vst(dds)

datExpr_vst = assay(vsd)
datMeta_vst = colData(vsd)
datGenes_vst = rowRanges(vsd)

rm(counts, rowRanges, se, vsd)

Using the plotting function DESEq2’s manual proposes to study vst’s output it looks like the data could be homoscedastic

meanSdPlot(datExpr_vst, plot=FALSE)$gg + theme_minimal()

When plotting point by point it seems like the group of genes with the lowest values behave differently to the rest

plot_data = data.frame('ID'=rownames(datExpr_vst), 'Mean'=rowMeans(datExpr_vst), 'SD'=apply(datExpr_vst,1,sd))

plot_data %>% ggplot(aes(Mean, SD)) + geom_point(color='#0099cc', alpha=0.2) + 
              scale_x_log10() + scale_y_log10() + theme_minimal()

rm(plot_data)

---

Save filtered and annotated dataset

*Could have done this since before

save(datExpr, datMeta, datGenes, file='./../Data/filtered_raw_data.RData')
#load('./../Data/filtered_raw_data.RData')

Rename normalised datasets to continue working with these

datExpr = datExpr_vst
datMeta = datMeta_vst %>% data.frame
datGenes = datGenes_vst

cat(paste0(length(unique(SFARI_genes$`gene-symbol`[SFARI_genes$ID %in% rownames(datExpr)])), ' SFARI genes remaining'))

## 931 SFARI genes remaining

cat(paste0('After filtering, the dataset consists of ', nrow(datExpr), ' genes and ', ncol(datExpr), ' samples'))

## After filtering, the dataset consists of 16490 genes and 21 samples

rm(datExpr_vst, datMeta_vst, datGenes_vst, datMeta_sva)

---

Batch Effect Correction

By including the surrogate variables in the DESeq formula we only modelled the batch effects into the DEA, but we didn’t actually correct them from the data, for that we need to use ComBat (or other equivalent package) in the already normalised data

SVA surrogate variables

In some places they say you shouldn’t correct these effects on the data because you risk losing biological variation, in others they say you should because they introduce noise to the data. The only thing everyone agrees on is that you shouldn’t remove them before performing DEA but instead include them in the model.

Based on the conclusions from Practical impacts of genomic data “cleaning” on biological discovery using surrogate variable analysis it seems like it may be a good idea to remove the batch effects from the data and not only from the DE analysis:

• Using SVA, ComBat or related tools can increase the power to identify specific signals in complex genomic datasets (they found “greatly sharpened global and gene-specific differential expression across treatment groups”)

• But caution should be exercised to avoid removing biological signal of interest

• We must be precise and deliberate in the design and analysis of experiments and the resulting data, and also mindful of the limitations we impose with our own perspective

• Open data exploration is not possible after such supervised “cleaning”, because effects beyond those stipulated by the researcher may have been removed

Comparing data with and without surrogate variable correction

# Taken from https://www.biostars.org/p/121489/#121500
correctDatExpr = function(datExpr, mod, svs) {
  X = cbind(mod, svs)
  Hat = solve(t(X) %*% X) %*% t(X)
  beta = (Hat %*% t(datExpr))
  rm(Hat)
  gc()
  P = ncol(mod)
  return(datExpr - t(as.matrix(X[,-c(1:P)]) %*% beta[-c(1:P),]))
}

pca_samples_before = datExpr %>% t %>% prcomp
pca_genes_before = datExpr %>% prcomp

# Correct
mod = model.matrix(~ Diagnosis, colData(dds))
svs = datMeta %>% dplyr::select(SV1:SV4) %>% as.matrix
datExpr_corrected = correctDatExpr(as.matrix(datExpr), mod, svs)

pca_samples_after = datExpr_corrected %>% t %>% prcomp
pca_genes_after = datExpr_corrected %>% prcomp

rm(correctDatExpr)

Samples

Removing batch effects has a big impact in the distribution of the samples, unlike the Frontal Lobe samples, they manage to separate perfectly by the first principal component after the SVA correction

pca_samples_df = rbind(data.frame('ID'=colnames(datExpr), 'PC1'=pca_samples_before$x[,1],
                                  'PC2'=pca_samples_before$x[,2], 'corrected'=0),
                       data.frame('ID'=colnames(datExpr), 'PC1'=pca_samples_after$x[,1],
                                  'PC2'=pca_samples_after$x[,2], 'corrected'=1)) %>%
                 left_join(datMeta %>% mutate('ID'=rownames(datMeta)), by='ID')

ggplotly(pca_samples_df %>% ggplot(aes(PC1, PC2, color=Diagnosis)) + geom_point(aes(frame=corrected, id=ID), alpha=0.75) + 
         xlab(paste0('PC1 (corr=', round(cor(pca_samples_before$x[,1],pca_samples_after$x[,1]),2),
                     '). % Var explained: ', round(100*summary(pca_samples_before)$importance[2,1],1),' to ',
                     round(100*summary(pca_samples_after)$importance[2,1],1))) +
         ylab(paste0('PC2 (corr=', round(cor(pca_samples_before$x[,2],pca_samples_after$x[,2]),2),
                     '). % Var explained: ', round(100*summary(pca_samples_before)$importance[2,2],1),' to ',
                     round(100*summary(pca_samples_after)$importance[2,2],1))) +
         ggtitle('Samples') + theme_minimal())

rm(pca_samples_df)

Genes

It seems like the sva correction preserves the mean expression of the genes and erases almost everything else (although what little else remains is enough to characterise the two Diagnosis groups pretty well using only the first PC)

*Plot is done with only 10% of the genes so it’s not that heavy

pca_genes_df = rbind(data.frame('ID'=rownames(datExpr), 'PC1'=pca_genes_before$x[,1],
                                'PC2'=pca_genes_before$x[,2], 'corrected'=0, 'MeanExpr'=rowMeans(datExpr)),
                     data.frame('ID'=rownames(datExpr), 'PC1'=pca_genes_after$x[,1],
                                'PC2'=pca_genes_after$x[,2], 'corrected'=1, 'MeanExpr'=rowMeans(datExpr)))

keep_genes = rownames(datExpr) %>% sample(0.1*nrow(datExpr))

pca_genes_df = pca_genes_df %>% filter(ID %in% keep_genes)

ggplotly(pca_genes_df %>% ggplot(aes(PC1, PC2,color=MeanExpr)) + geom_point(alpha=0.3, aes(frame=corrected, id=ID)) +
         xlab(paste0('PC1 (corr=', round(cor(pca_genes_before$x[,1],pca_genes_after$x[,1]),2),
                     '). % Var explained: ', round(100*summary(pca_genes_before)$importance[2,1],1),' to ',
                     round(100*summary(pca_genes_after)$importance[2,1],1))) +
         ylab(paste0('PC2 (corr=', round(cor(pca_genes_before$x[,2],pca_genes_after$x[,2]),2),
                     '). % Var explained: ', round(100*summary(pca_genes_before)$importance[2,2],1),' to ',
                     round(100*summary(pca_genes_after)$importance[2,2],1))) +
         scale_color_viridis() + ggtitle('Genes') + theme_minimal())

rm(pca_samples_before, pca_genes_before, mod, svs, pca_samples_after, pca_genes_after, pca_genes_df, keep_genes)

Everything looks good, so we’re keeping the corrected expression dataset

datExpr = datExpr_corrected

rm(datExpr_corrected)

Processing date

Even after correcting the dataset for the surrogate variables found with sva, there is still a difference in mean expression by processing date (although this difference is relatively small)

Since the processing date and Diagnosis are correlated and because we know from the exploratory analysis of the whole dataset that ASD samples tend to have higher levels of expression than the controls, we cannot tell if the difference we are seeing is coming from the Diagnosis or from the Batch effect (because the curve with the lower level of expression corresponds to the batch with the majority of the CTL samples). Because of this, I’m not going to correct for processing date.

plot_data_b1 = data.frame('Mean'=colMeans(datExpr[,datMeta$RNAExtractionBatch=='10/10/2014']), 'Batch'='10/10/2014')
plot_data_b2 = data.frame('Mean'=colMeans(datExpr[,datMeta$RNAExtractionBatch=='6/20/2014']), 'Batch'='6/20/2014')

plot_data = rbind(plot_data_b1, plot_data_b2)
mu = plot_data %>% group_by(Batch) %>% dplyr::summarise(BatchMean=mean(Mean))

ggplotly(plot_data %>% ggplot(aes(x=Mean, color=Batch, fill=Batch)) + geom_density(alpha=0.3) + 
         geom_vline(data=mu, aes(xintercept=BatchMean, color=Batch), linetype='dashed') +
         ggtitle('Mean expression by sample grouped by processing date') + scale_x_log10() + theme_minimal())

rm(plot_data_b1, plot_data_b2, plot_data, mu)

---

Save preprocessed dataset

save(datExpr, datMeta, datGenes, DE_info, dds, file='./../Data/preprocessed_data.RData')
#load('./../Data/preprocessed_data.RData')

---

Session info

sessionInfo()

## R version 3.6.0 (2019-04-26)
## Platform: x86_64-redhat-linux-gnu (64-bit)
## Running under: Scientific Linux 7.6 (Nitrogen)
## 
## Matrix products: default
## BLAS/LAPACK: /usr/lib64/R/lib/libRblas.so
## 
## locale:
##  [1] LC_CTYPE=en_GB.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_GB.UTF-8        LC_COLLATE=en_GB.UTF-8    
##  [5] LC_MONETARY=en_GB.UTF-8    LC_MESSAGES=en_GB.UTF-8   
##  [7] LC_PAPER=en_GB.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_GB.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] parallel  stats4    stats     graphics  grDevices utils     datasets 
## [8] methods   base     
## 
## other attached packages:
##  [1] knitr_1.24                  expss_0.10.1               
##  [3] dendextend_1.13.3           vsn_3.54.0                 
##  [5] WGCNA_1.68                  fastcluster_1.1.25         
##  [7] dynamicTreeCut_1.63-1       sva_3.34.0                 
##  [9] genefilter_1.68.0           mgcv_1.8-28                
## [11] nlme_3.1-139                DESeq2_1.26.0              
## [13] SummarizedExperiment_1.16.1 DelayedArray_0.12.2        
## [15] BiocParallel_1.20.1         matrixStats_0.55.0         
## [17] Biobase_2.46.0              GenomicRanges_1.38.0       
## [19] GenomeInfoDb_1.22.0         IRanges_2.20.2             
## [21] S4Vectors_0.24.3            BiocGenerics_0.32.0        
## [23] biomaRt_2.42.0              ggpubr_0.2.5               
## [25] magrittr_1.5                ggExtra_0.9                
## [27] GGally_1.4.0                gridExtra_2.3              
## [29] viridis_0.5.1               viridisLite_0.3.0          
## [31] RColorBrewer_1.1-2          plotlyutils_0.0.0.9000     
## [33] plotly_4.9.2                glue_1.3.1                 
## [35] reshape2_1.4.3              forcats_0.4.0              
## [37] stringr_1.4.0               dplyr_0.8.3                
## [39] purrr_0.3.3                 readr_1.3.1                
## [41] tidyr_1.0.2                 tibble_2.1.3               
## [43] ggplot2_3.2.1               tidyverse_1.3.0            
## 
## loaded via a namespace (and not attached):
##   [1] tidyselect_0.2.5       robust_0.4-18.2        RSQLite_2.2.0         
##   [4] AnnotationDbi_1.48.0   htmlwidgets_1.5.1      grid_3.6.0            
##   [7] munsell_0.5.0          codetools_0.2-16       preprocessCore_1.48.0 
##  [10] miniUI_0.1.1.1         withr_2.1.2            colorspace_1.4-1      
##  [13] highr_0.8              rstudioapi_0.10        robustbase_0.93-5     
##  [16] ggsignif_0.6.0         labeling_0.3           GenomeInfoDbData_1.2.2
##  [19] bit64_0.9-7            farver_2.0.3           vctrs_0.2.2           
##  [22] generics_0.0.2         xfun_0.8               BiocFileCache_1.10.2  
##  [25] R6_2.4.1               doParallel_1.0.15      locfit_1.5-9.1        
##  [28] bitops_1.0-6           reshape_0.8.8          assertthat_0.2.1      
##  [31] promises_1.1.0         scales_1.1.0           nnet_7.3-12           
##  [34] gtable_0.3.0           Cairo_1.5-10           affy_1.64.0           
##  [37] rlang_0.4.4            splines_3.6.0          lazyeval_0.2.2        
##  [40] acepack_1.4.1          impute_1.60.0          hexbin_1.28.1         
##  [43] broom_0.5.4            checkmate_1.9.4        BiocManager_1.30.10   
##  [46] yaml_2.2.0             modelr_0.1.5           crosstalk_1.0.0       
##  [49] backports_1.1.5        httpuv_1.5.2           Hmisc_4.2-0           
##  [52] tools_3.6.0            affyio_1.56.0          ellipsis_0.3.0        
##  [55] Rcpp_1.0.3             plyr_1.8.5             base64enc_0.1-3       
##  [58] progress_1.2.2         zlibbioc_1.32.0        RCurl_1.95-4.12       
##  [61] prettyunits_1.0.2      rpart_4.1-15           openssl_1.4.1         
##  [64] cowplot_1.0.0          haven_2.2.0            cluster_2.0.8         
##  [67] fs_1.3.1               data.table_1.12.8      reprex_0.3.0          
##  [70] mvtnorm_1.0-11         hms_0.5.3              mime_0.9              
##  [73] evaluate_0.14          xtable_1.8-4           XML_3.99-0.3          
##  [76] readxl_1.3.1           compiler_3.6.0         crayon_1.3.4          
##  [79] htmltools_0.4.0        pcaPP_1.9-73           later_1.0.0           
##  [82] Formula_1.2-3          geneplotter_1.64.0     rrcov_1.4-7           
##  [85] lubridate_1.7.4        DBI_1.1.0              dbplyr_1.4.2          
##  [88] MASS_7.3-51.4          rappdirs_0.3.1         Matrix_1.2-17         
##  [91] cli_2.0.1              pkgconfig_2.0.3        fit.models_0.5-14     
##  [94] foreign_0.8-71         xml2_1.2.2             foreach_1.4.7         
##  [97] annotate_1.64.0        XVector_0.26.0         rvest_0.3.5           
## [100] digest_0.6.24          rmarkdown_1.14         cellranger_1.1.0      
## [103] htmlTable_1.13.1       curl_4.3               shiny_1.4.0           
## [106] lifecycle_0.1.0        jsonlite_1.6           askpass_1.1           
## [109] limma_3.42.2           fansi_0.4.1            pillar_1.4.3          
## [112] lattice_0.20-38        fastmap_1.0.1          httr_1.4.1            
## [115] DEoptimR_1.0-8         survival_2.44-1.1      GO.db_3.10.0          
## [118] iterators_1.0.12       bit_1.1-15.2           stringi_1.4.6         
## [121] blob_1.2.1             latticeExtra_0.6-28    memoise_1.1.0